Groupwise registration with global-local graph shrinkage in atlas construction

• Published in: Medical image analysis Vol. 64; p. 101711
• Main Authors: Fu, Tianyu, Yang, Jian, Li, Qin, Ai, Danni, Song, Hong, Jiang, Yurong, Wang, Yongtian, Frangi, Alejandro F.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.08.2020
• Subjects: Atlas construction; Global-local; Graph shrinkage; Groupwise registration; Graph shrinkage; Atlas construction; Global-local; Groupwise registration
• ISSN: 1361-8415; 1361-8423; 1361-8423
• DOI: 10.1016/j.media.2020.101711

•A graph is automatically constructed to model the global distribution of the dataset on the image manifold without a priori template.•A higher computational efficiency is achieved by maintaining the local distributions on the image manifold.•The accuracy of the resultant atlas is improved by capturing both global and local structural variations among images during graph shrinkage.•Compared with six state-of-the-art methods on synthetic and clinical datasets, results of the proposed method show a competitive performance. Graph-based groupwise registration methods are widely used in atlas construction. Given a group of images, a graph is built whose nodes represent the images, and whose edges represent a geodesic path between two nodes. The distribution of images on an image manifold is explored through edge traversal in a graph. The final atlas is a mean image at the population center of the distribution on the manifold. The procedure of warping all images to the mean image turns to dynamic graph shrinkage in which nodes become closer to each other. Most conventional groupwise registration frameworks construct and shrink a graph without considering the local distribution of images on the dataset manifold and the local structure variations between image pairs. Neglecting the local information fundamentally decrease the accuracy and efficiency when population atlases are built for organs with large inter-subject anatomical variabilities. To overcome the problem, this paper proposes a global-local graph shrinkage approach that can generate accurate atlas. A connected graph is constructed automatically based on global similarities across the images to explore the global distribution. A local image distribution obtained by image clustering is used to simplify the edges of the constructed graph. Subsequently, local image similarities refine the deformation estimated through global image similarity for each image warping along the graph edges. Through the image warping, the overall simplified graph shrinks gradually to yield the atlas with respecting both global and local features. The proposed method is evaluated on 61 synthetic and 20 clinical liver datasets, and the results are compared with those of six state-of-the-art groupwise registration methods. The experimental results show that the proposed method outperforms non-global-local method approaches in terms of accuracy. [Display omitted]